{"id":"W4390604119","doi":"10.1109/tpami.2024.3350450","title":"Regularized Loss With Hyperparameter Estimation for Weakly Supervised Single Class Segmentation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Hyperparameter; Segmentation; Computer science; Pattern recognition (psychology); Image segmentation; Conditional random field; Ground truth; Pixel; Machine learning; Scale-space segmentation","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001178989,0.0001965207,0.0002182642,0.0003560377,0.0001943795,0.0002705665,0.0002461774,0.00004871559,0.00002462388],"category_scores_gemma":[0.000002225851,0.0001584171,0.0001575169,0.001255697,0.00006143424,0.0004542277,0.000003297473,0.0001448319,0.00001456817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005291189,"about_ca_system_score_gemma":0.00001632797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000638443,"about_ca_topic_score_gemma":0.0002839373,"domain_scores_codex":[0.9987033,0.00004197283,0.0002903308,0.0005902587,0.0001792861,0.000194868],"domain_scores_gemma":[0.9990946,0.0002922394,0.00005846584,0.0004007225,0.00007136037,0.00008259532],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002221737,0.00009024397,0.00002391817,0.00002923799,0.000275551,0.000003564937,0.0001674526,0.1814259,0.004298161,0.0004520648,0.000006166886,0.8132055],"study_design_scores_gemma":[0.00008517968,0.0001644112,0.00003900818,0.00002689915,0.0003432861,0.00001348745,0.00001210802,0.8514155,0.1463531,0.001304846,0.00007013237,0.0001719947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006474562,0.00006963922,0.9915601,0.001162836,0.0001083808,0.0003779445,0.00003892111,0.0001947966,0.0000128418],"genre_scores_gemma":[0.9081417,0.00006566041,0.09112974,0.0002513783,0.00001510446,0.0001987587,0.00002333844,0.00001612332,0.0001581652],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9016672,"threshold_uncertainty_score":0.6460062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02345517721428979,"score_gpt":0.2795068314920156,"score_spread":0.2560516542777257,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}